KoalaTrapLord 3957285a2e feat(ml): add PPO DecisionExporter for closed-loop distillation (#65) ...

Phase 1 of closed-loop distillation pipeline.

Adds DecisionExporter class that captures PPO self-play decisions
as JSONL files compatible with the Forge DecisionSnapshot schema.
Includes PPO-specific metadata fields (source, model_version,
reward, episode_return) and configurable win-only filtering.

2026-03-21 18:06:45 -04:00

..

__init__.py

Initial commit

2026-03-10 12:13:56 -04:00

decision_exporter.py

feat(ml): add PPO DecisionExporter for closed-loop distillation (#65)

2026-03-21 18:06:45 -04:00

policy_network.py

refactor: adopt Python logging module with named loggers

2026-03-13 18:09:52 +00:00

ppo_trainer.py

Initial commit

2026-03-10 12:13:56 -04:00

reward.py

Initial commit

2026-03-10 12:13:56 -04:00

rollout_buffer.py

Initial commit

2026-03-10 12:13:56 -04:00

self_play.py

Initial commit

2026-03-10 12:13:56 -04:00

trainer.py

refactor: adopt Python logging module with named loggers

2026-03-13 18:09:52 +00:00